Arianne Reimerink

Representing environmental knowledge in ecolexicon

EcoLexicon is a multilingual terminological knowledge base (TKB) on the environment, which provides an internally coherent information system covering a wide range of specialized linguistic and conceptual needs. Our research has mainly focused on conceptual modeling with a view to offering a user-friendly multimodal interface. The dynamic interface of EcoLexicon combines conceptual, linguistic, and graphical information and is primarily hosted in a relational database that has been recently linked to an ontology. One of the main challenges that we have faced in the development of our TKB is the information overload generated by the specialized domain. This is not only due to the wide scope and applicability of environmental concepts, but especially to the fact that multiple dimensions of their meaning definition or conceptual description are not always compatible but rather context-dependent. As a result, concepts with an information overload have been reconceptualized according to two contextual factors: domain membership and semantic role. This reduces the amount of conceptual information accessed by the user, and makes the knowledge representation easier to process.

Multidimensional and Multimodal Information in EcoLexicon

EcoLexicon is a multilingual terminological knowledge base (TKB) on the environment that targets different user groups who wish to expand their knowledge of the environment for the purpose of text comprehension and/or generation. Users can freely access EcoLexicon, and are able to find the information needed, thanks to a user-friendly visual interface with different modules for conceptual, linguistic, and graphical data. The main goal of this TKB is user knowledge acquisition. This paper briefly explains the theoretical premises and methodology applied in EcoLexicon for knowledge extraction and representation. It also shows how environmental concepts are represented, interrelated, and contextualized. EcoLexicon combines the advantages of a relational database, allowing for a quick deployment and feeding of the platform, and an ontology, enhancing user queries. The internal coherence at all levels of a dynamic knowledge representation shows that even complex domains can be represented in a user-friendly way.

Predicate-Argument Analysis to Build a Phraseology Module and to Increase Conceptual Relation Expressiveness.

EcoLexicon, a multilingual and multimodal terminological knowledge base (TKB) on the environment, needs improvements: more expressive non-hierarchical relations and a phraseology module consistent with knowledge representation in the other modules of the TKB. Both issues must be addressed by analyzing predicate-argument structure in text. In this paper, we explain our methodology for predicate-argument analysis with the case study on the conceptual relation affects. We take a semi-automatic approach to extract term-verb-term collocates with Sketch Engine [1]. Then the verbs are classified according to the lexical domains proposed by Faber & Mairal [2] and the arguments in conceptual categories based on the knowledge contained in EcoLexicon. To validate the lexical domains and conceptual categories, an automatic clustering method based on word2vec [3] is applied. The analysis of verbs and arguments contributes to the refinement of our semantic relations and categories as well as to the population of the phraseological module.

Image selection and annotation for an environmental knowledge base

Images play an important role in the representation and acquisition of specialized knowledge. Not surprisingly, terminological knowledge bases (TKBs) often include images as a way to enhance the information in concept entries. However, the selection of these images should not be random, but rather based on specific guidelines that take into account the type and nature of the concept being described. This paper presents a proposal on how to combine the features of images with the conceptual propositions in EcoLexicon, a multilingual TKB on the environment. This proposal is based on the following: (1) the combinatory possibilities of concept types; (2) image types, such as photographs, drawings and flow charts; (3) morphological features or visual knowledge patterns (VKPs), such as labels, colours, arrows, and their effect on the functional nature of each image type. Currently, images are stored in association with concept entries according to the semantic content of their definitions, but they are not described or annotated according to the parameters that guided their selection, which would undoubtedly contribute to the systematization and automatization of the process. First, the images included in EcoLexicon were analyzed in terms of their adequateness, the semantic relations expressed, the concept types and their VKPs. Then, with these data, guidelines for image selection and annotation were created. The final aim is twofold: (1) to systematize the selection of images and (2) to start annotating old and new images so that the system can automatically allocate them in different concept entries based on shared conceptual propositions.